Name
Abstract | ||
|---|---|---|
Recurrent networks of polynomial threshold elements with random symmetric interactions are studied. Precise asymptotic estimates are derived for the expected number of fixed points as a function of the margin of stability. In particular, it is shown that there is a critical range of margins of stability (depending on the degree of polynomial interaction) such that the expected number of fixed points with margins below the critical range grows exponentially with the number of nodes in the network, while the expected number of fixed points with margins above the critical range decreases exponentially with the number of nodes in the network. The random energy model is also briefly examined, and links with higher-order neural networks and higher-order spin glass models are made explicit |
Year | DOI | Venue |
|---|---|---|
1993 | 10.1109/18.179374 | Information Theory, IEEE Transactions |
Keywords | Field | DocType |
polynomials,random processes,recurrent neural nets,higher order neural networks,higher-order spin glass models,margin of stability,number of fixed points,polynomial threshold elements,random energy model,random symmetric interactions,recurrent networks | Discrete mathematics,Combinatorics,Fixed-point arithmetic,Polynomial,Stochastic process,Random energy model,Degree of a polynomial,Expected value,Fixed point,Artificial neural network,Mathematics | Journal |
Volume | Issue | ISSN |
39 | 1 | 0018-9448 |
Citations | PageRank | References |
3 | 0.54 | 7 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Baldi, P. | 1 | 3 | 0.54 |
| Santosh S. Venkatesh | 2 | 381 | 71.80 |